parliamentary-nlp-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HF_TOKEN | No | Hugging Face token. Only required if the model checkpoint is private. | |
| PARLIAMENTARY_NLP_MODEL_ID | No | Hugging Face model identifier. Overrides the default model checkpoint. | alissonf216/parliamentary-bertimbau-auditor |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_parliamentary_speechA | Audit Portuguese parliamentary or political speech for offensive content. Use this tool whenever a user asks you to analyse, moderate, classify, or safety-check political / legislative discourse in Portuguese (PT-BR), including floor speeches, committee interventions, social-media posts by elected officials, and campaign rhetoric. The underlying BERTimbau-based classifier estimates:
Args: text: Raw Portuguese utterance or transcript excerpt to audit. Returns:
Structured audit dictionary with |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion. The tool's purpose is clearly defined and covers the entire domain of auditing parliamentary speech.
The single tool name 'audit_parliamentary_speech' follows a clear verb_object pattern. Although there is only one example, the naming is consistent with common conventions.
The server has just one tool, which is on the thin end of the range. For a domain like parliamentary speech analysis, one might expect additional tools (e.g., for summarizing or extracting topics), but for the stated auditing purpose, a single tool can be acceptable.
The tool provides a comprehensive audit result including classification, confidence, entropy, and a human-review flag, covering all stated use cases (analyse, moderate, classify, safety-check). There are no obvious dead ends within the tool's intended scope.